Difference between revisions of "ArtEx"
(Created blank page) |
|||
| (One intermediate revision by the same user not shown) | |||
| Line 1: | Line 1: | ||
| + | Modern recommender systems (RecSys), particularly those using deep learning, often lack transparency and user control, functioning as black boxes that may create filter bubbles or prioritize revenue over user preferences. In visual art recommendation systems (VA RecSys), where diversity and exploration are critical, this opacity can hinder user engagement. ArtEx addresses these challenges by providing a web-based platform that empowers users to control recommendation attributes like popularity and diversity through adjustable sliders. | ||
| + | ArtEx is an interactive interface designed to showcase user-driven personalization. Built on the SemArt dataset and leveraging BLIP’s multimodal features as a backbone, ArtEx enables users to explore a rich collection of artworks by solving joint optimization problems to facilitate the control of popularity and diversity of items allowing users to fine-tune recommendations to align with their preferences. | ||
| + | |||
| + | [[File:recsys25-241-fig3.jpg]] | ||
| + | |||
| + | [[File:umapadjunct25-20-fig2.jpg]] | ||
| + | |||
| + | == Publications == | ||
| + | |||
| + | * Rully Agus Hendrawan, Peter Brusilovsky, Luis A. Leiva, and Bereket A. Yilma. 2025. ArtEx: A User-Controllable Web Interface for Visual Art Recommendations. In Proceedings of the Nineteenth ACM Conference on Recommender Systems (RecSys '25). Association for Computing Machinery, New York, NY, USA, 1328–1330. ([https://doi.org/10.1145/3705328.3759343 paper]) | ||
| + | * Rully Agus Hendrawan, Peter Brusilovsky, Bereket A. Yilma, and Luis A. Leiva. 2025. Recommending Paintings in Web Art Gallery with Adjustable Popularity and Diversity. In Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization (UMAP Adjunct '25). Association for Computing Machinery, New York, NY, USA, 449–458. ([https://doi.org/10.1145/3708319.3733649 paper]) | ||
Latest revision as of 18:34, 4 March 2026
Modern recommender systems (RecSys), particularly those using deep learning, often lack transparency and user control, functioning as black boxes that may create filter bubbles or prioritize revenue over user preferences. In visual art recommendation systems (VA RecSys), where diversity and exploration are critical, this opacity can hinder user engagement. ArtEx addresses these challenges by providing a web-based platform that empowers users to control recommendation attributes like popularity and diversity through adjustable sliders.
ArtEx is an interactive interface designed to showcase user-driven personalization. Built on the SemArt dataset and leveraging BLIP’s multimodal features as a backbone, ArtEx enables users to explore a rich collection of artworks by solving joint optimization problems to facilitate the control of popularity and diversity of items allowing users to fine-tune recommendations to align with their preferences.
Publications
- Rully Agus Hendrawan, Peter Brusilovsky, Luis A. Leiva, and Bereket A. Yilma. 2025. ArtEx: A User-Controllable Web Interface for Visual Art Recommendations. In Proceedings of the Nineteenth ACM Conference on Recommender Systems (RecSys '25). Association for Computing Machinery, New York, NY, USA, 1328–1330. (paper)
- Rully Agus Hendrawan, Peter Brusilovsky, Bereket A. Yilma, and Luis A. Leiva. 2025. Recommending Paintings in Web Art Gallery with Adjustable Popularity and Diversity. In Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization (UMAP Adjunct '25). Association for Computing Machinery, New York, NY, USA, 449–458. (paper)
